trainReco: Parallelized Recosystem
In Pooja-Rajkumar/rectools: Advanced Recommender System

Description Usage Arguments Details Author(s) Examples

Convenience wrappers for specific aspects of the recosystem package, adding a parallel computation capability.

1 2	trainReco(ratingsIn,rnk = 10) predict.Reco(recoObj,predSet)

`ratingsIn`	Input data frame, training set. Within-row format is (UserID, ItemID, rating).
`recoObj`	Object of type `'Reco'`, output of `trainReco`.
`predSet`	Data to be predicted, having within-row format (UserID, ItemID).
`rnk`	Desired rank for the matrix factors.

The function trainReco simply calls r$train on the input data.

The latter function returns several key components, including:

P: This is the user score matrix, in which a row represents a user, and each column is a latent factor.
Q: This is the item score matrix, in which a row represents an item, and each column is a latent factor.

The product of these two matricies consists of the predicted ratings of all users on all items.

The function predict.Reco is a method for the generic function predict.

Pooja Rajkumar and Norm Matloff

   ivl <- InstEval 
   ivl$s <- as.numeric(ivl$s) 
   ivl$d <- as.numeric(ivl$d) 
   ivl3 <- ivl[,c(1,2,7)]
   set.seed(9999)
   trn <- trainReco(ivl3)
   onerec <- ivl3[1,]  # form dummy 1-rec data frame
   # how would student 788 would like lecturer 28?
   onerec$s <- 788  
   onerec$d <- 28  
   onerec <- onerec[,-3]
   predict(trn,onerec)  # 1.49